mm: fix khugepaged activation policy

Since the introduction of mTHP, the docuementation has stated that
khugepaged would be enabled when any mTHP size is enabled, and disabled
when all mTHP sizes are disabled.  There are 2 problems with this; 1. 
this is not what was implemented by the code and 2.  this is not the
desirable behavior.

Desirable behavior is for khugepaged to be enabled when any PMD-sized THP
is enabled, anon or file.  (Note that file THP is still controlled by the
top-level control so we must always consider that, as well as the PMD-size
mTHP control for anon).  khugepaged only supports collapsing to PMD-sized
THP so there is no value in enabling it when PMD-sized THP is disabled. 
So let's change the code and documentation to reflect this policy.

Further, per-size enabled control modification events were not previously
forwarded to khugepaged to give it an opportunity to start or stop. 
Consequently the following was resulting in khugepaged eroneously not
being activated:

  echo never > /sys/kernel/mm/transparent_hugepage/enabled
  echo always > /sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled

[ryan.roberts@arm.com: v3]
  Link: https://lkml.kernel.org/r/20240705102849.2479686-1-ryan.roberts@arm.com
Link: https://lkml.kernel.org/r/20240705102849.2479686-1-ryan.roberts@arm.com
Link: https://lkml.kernel.org/r/20240704091051.2411934-1-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Fixes: 3485b88390b0 ("mm: thp: introduce multi-size THP sysfs interface")
Closes: https://lore.kernel.org/linux-mm/7a0bbe69-1e3d-4263-b206-da007791a5c4@redhat.com/
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 33 insertions, 7 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 17fb072a0ca1..f8b5cbd4dd71 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -502,6 +502,13 @@ static ssize_t thpsize_enabled_store(struct kobject *kobj,
 	} else
 		ret = -EINVAL;
 
+	if (ret > 0) {
+		int err;
+
+		err = start_stop_khugepaged();
+		if (err)
+			ret = err;
+	}
 	return ret;
 }
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 409f67a817f1..a5ec03ef8722 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -413,6 +413,26 @@ static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm)
 	       test_bit(MMF_DISABLE_THP, &mm->flags);
 }
 
+static bool hugepage_pmd_enabled(void)
+{
+	/*
+	 * We cover both the anon and the file-backed case here; file-backed
+	 * hugepages, when configured in, are determined by the global control.
+	 * Anon pmd-sized hugepages are determined by the pmd-size control.
+	 */
+	if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
+	    hugepage_global_enabled())
+		return true;
+	if (test_bit(PMD_ORDER, &huge_anon_orders_always))
+		return true;
+	if (test_bit(PMD_ORDER, &huge_anon_orders_madvise))
+		return true;
+	if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) &&
+	    hugepage_global_enabled())
+		return true;
+	return false;
+}
+
 void __khugepaged_enter(struct mm_struct *mm)
 {
 	struct khugepaged_mm_slot *mm_slot;
@@ -449,7 +469,7 @@ void khugepaged_enter_vma(struct vm_area_struct *vma,
 			  unsigned long vm_flags)
 {
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
-	    hugepage_flags_enabled()) {
+	    hugepage_pmd_enabled()) {
 		if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS,
 					    PMD_ORDER))
 			__khugepaged_enter(vma->vm_mm);
@@ -2462,8 +2482,7 @@ breakouterloop_mmap_lock:
 
 static int khugepaged_has_work(void)
 {
-	return !list_empty(&khugepaged_scan.mm_head) &&
-		hugepage_flags_enabled();
+	return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled();
 }
 
 static int khugepaged_wait_event(void)
@@ -2536,7 +2555,7 @@ static void khugepaged_wait_work(void)
 		return;
 	}
 
-	if (hugepage_flags_enabled())
+	if (hugepage_pmd_enabled())
 		wait_event_freezable(khugepaged_wait, khugepaged_wait_event());
 }
 
@@ -2567,7 +2586,7 @@ static void set_recommended_min_free_kbytes(void)
 	int nr_zones = 0;
 	unsigned long recommended_min;
 
-	if (!hugepage_flags_enabled()) {
+	if (!hugepage_pmd_enabled()) {
 		calculate_min_free_kbytes();
 		goto update_wmarks;
 	}
@@ -2617,7 +2636,7 @@ int start_stop_khugepaged(void)
 	int err = 0;
 
 	mutex_lock(&khugepaged_mutex);
-	if (hugepage_flags_enabled()) {
+	if (hugepage_pmd_enabled()) {
 		if (!khugepaged_thread)
 			khugepaged_thread = kthread_run(khugepaged, NULL,
 							"khugepaged");
@@ -2643,7 +2662,7 @@ fail:
 void khugepaged_min_free_kbytes_update(void)
 {
 	mutex_lock(&khugepaged_mutex);
-	if (hugepage_flags_enabled() && khugepaged_thread)
+	if (hugepage_pmd_enabled() && khugepaged_thread)
 		set_recommended_min_free_kbytes();
 	mutex_unlock(&khugepaged_mutex);
 }